Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Object detection via feature synthesis using MDL-based genetic programming.

Yingqiang Lin, Bir Bhanu

    IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
    |June 24, 2005
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Toward Generative Understanding: Incremental Few-Shot Semantic Segmentation With Diffusion Models.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Sampling Conformational Ensembles of Highly Dynamic Proteins via Generative Deep Learning.

    Journal of chemical information and modeling·2025
    Same author

    Computational modeling of tumor invasion from limited and diverse data in Glioblastoma.

    Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2024
    Same author

    Sampling Conformational Ensembles of Highly Dynamic Proteins via Generative Deep Learning.

    Research square·2024
    Same author

    Sampling Conformational Ensembles of Highly Dynamic Proteins via Generative Deep Learning.

    bioRxiv : the preprint server for biology·2024
    Same author

    RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation.

    IEEE transactions on pattern analysis and machine intelligence·2024

    Genetic programming (GP) creates novel composite operators for object detection, overcoming human limitations. This enhanced GP approach improves efficiency and effectiveness in identifying objects.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Human experts often limit feature synthesis to conventional combinations of primitive image processing operations.
    • Object detection relies on effective feature extraction, which can be constrained by human expertise.
    • Genetic programming (GP) offers a method to explore unconventional combinations for feature synthesis.

    Purpose of the Study:

    • To synthesize novel composite operators and features for object detection using genetic programming (GP).
    • To overcome limitations of human experts in feature synthesis by exploring unconventional combinations.
    • To improve the efficiency and effectiveness of GP for object detection tasks.

    Main Methods:

    • Utilized genetic programming (GP) to automatically generate composite operators and features.

    Related Experiment Videos

  • Developed a new fitness function based on the minimum description length (MDL) principle to balance pixel labeling error and operator size.
  • Incorporated smart crossover, smart mutation, and a public library concept to enhance GP efficiency and prevent code bloat.
  • Conducted experiments on training image regions to reduce training time and validated on whole images and testing sets.

    • Main Results:

    • The proposed GP algorithm discovered effective composite operators more rapidly than standard GP.
    • Learned composite operators demonstrated superior performance when applied to the entire training image and similar testing images.
    • GP-derived composite operators proved more effective and efficient for object detection compared to traditional region-of-interest extraction algorithms.

    Conclusions:

    • GP is a powerful tool for synthesizing effective composite operators and features in object detection.
    • The enhanced GP approach, incorporating MDL-based fitness and efficiency improvements, significantly accelerates the discovery of optimal operators.
    • This method surpasses traditional algorithms in both effectiveness and efficiency for object detection.